1. Assessment of Severe Apnoea through Voice Analysis, Automatic Speech, and Speaker Recognition Techniques
- Author
-
Luis A. Hernández Gómez, José Luis Blanco Murillo, José Alcázar Ramírez, Eduardo López Gonzalo, Rubén Fernández Pozo, Doroteo Torre Toledano, [Fernández Pozo,R, Blanco Murillo,JL, Hernández Gómez,L, López Gonzalo,E] Signal, Systems and Radiocommunications Departament, Universidad Politécnica de Madrid, Madrid, Spain. [Alcázar Ramírez,J] Respiratory Departament, Hospital Torrecárdenas, Almería, Spain. [Toledano,DT] ATVS Biometric Recognition group, Universidad Autónoma de Madrid, Madrid, Spain., The activities described in this paper were funded by the Spanish Ministry of Science and Technology as part of the TEC2006-13170-C02-02 Project., UAM. Departamento de Ingeniería Informática, and Análisis y Tratamiento de Voz y Señales Biométricas (ING EPS-002)
- Subjects
Sustained speech ,Artificial intelligence ,Information Science::Information Science::Computing Methodologies::Software::Speech Recognition Software [Medical Subject Headings] ,Computer science ,Speech recognition ,0206 medical engineering ,lcsh:TK7800-8360 ,02 engineering and technology ,computer.software_genre ,Voice analysis ,Nasalization ,lcsh:Telecommunication ,Vowel ,lcsh:TK5101-6720 ,0202 electrical engineering, electronic engineering, information engineering ,Distribución normal ,Diseases::Respiratory Tract Diseases::Respiration Disorders::Apnea::Sleep Apnea Syndromes::Sleep Apnea, Obstructive [Medical Subject Headings] ,Audio signal processing ,Telecomunicaciones ,Phenomena and Processes::Mathematical Concepts::Statistical Distributions::Normal Distribution [Medical Subject Headings] ,lcsh:Electronics ,020206 networking & telecommunications ,Phonetics ,Speaker recognition ,Speech processing ,Diseases::Otorhinolaryngologic Diseases::Laryngeal Diseases::Voice Disorders [Medical Subject Headings] ,020601 biomedical engineering ,Continuous speech ,Obstructive sleep apnea ,respiratory tract diseases ,Apnea del sueño obstructiva ,Pattern recognition (psychology) ,Speech dynamics ,Gaussian mixture models ,computer ,Programa informático para el reconocimiento del lenguaje hablado ,Trastornos de la voz ,Classification and regression tree (CART) - Abstract
The electronic version of this article is the complete one and can be found online at: http://asp.eurasipjournals.com/content/2009/1/982531, This study is part of an ongoing collaborative effort between the medical and the signal processing communities to promote research on applying standard Automatic Speech Recognition (ASR) techniques for the automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases is important so that patients can receive early treatment. Effective ASR-based detection could dramatically cut medical testing time. Working with a carefully designed speech database of healthy and apnoea subjects, we describe an acoustic search for distinctive apnoea voice characteristics. We also study abnormal nasalization in OSA patients by modelling vowels in nasal and nonnasal phonetic contexts using Gaussian Mixture Model (GMM) pattern recognition on speech spectra. Finally, we present experimental findings regarding the discriminative power of GMMs applied to severe apnoea detection. We have achieved an 81% correct classification rate, which is very promising and underpins the interest in this line of inquiry., The activities described in this paper were funded by the Spanish Ministry of Science and Technology as part of the TEC2006-13170-C02-02 Project.
- Published
- 2009